• Pawanjit Kaur
• Anita Suman
• Parveen Kumar

Face recognition play a significant role in real time imaging systems for various applications. This approach is much popular in many of the fields the main and the important one is recognition or can say as the security or authentication purpose. To implement the objective of this dissertation, initially region of interest (ROI) technique is used to extract the faces from the images. Thereafter, Kernel PCA is used to replace the traditional PCA feature extraction process. Artificial Intelligence based multi layered neural network is then implemented for classification of faces. The proposed and the existing technique is tested on the MATLAB 2013a tool with the help of image processing toolbox. Extensive experiments have been done by considering benchmark and real-life images. It has been found that the proposed technique outperforms existing techniques in terms of the F measure, Sensitivity, Specificity, Accuracy, and G-accuracy. Therefore, the proposed technique is more efficient for real-time imaging systems.

Face recognition, multi-layered neural network, PCA and feature extraction.

"Multi-layered ANN Region of Interest Approach with Enhanced PCA for Face Recognition ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.571-577, July-2018, Available :http://www.jetir.org/papers/JETIR1807543.pdf

"Multi-layered ANN Region of Interest Approach with Enhanced PCA for Face Recognition ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 7, page no. pp571-577, July-2018, Available at : http://www.jetir.org/papers/JETIR1807543.pdf